CN112693474A - Perception system diagnostics using predicted sensor data and perception results - Google Patents

Perception system diagnostics using predicted sensor data and perception results Download PDF

Info

Publication number
CN112693474A
CN112693474A CN202011148960.4A CN202011148960A CN112693474A CN 112693474 A CN112693474 A CN 112693474A CN 202011148960 A CN202011148960 A CN 202011148960A CN 112693474 A CN112693474 A CN 112693474A
Authority
CN
China
Prior art keywords
sensor data
perception
predicted
result
module
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011148960.4A
Other languages
Chinese (zh)
Inventor
胡峣
佟维
林玟樵
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
GM Global Technology Operations LLC
Original Assignee
GM Global Technology Operations LLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by GM Global Technology Operations LLC filed Critical GM Global Technology Operations LLC
Publication of CN112693474A publication Critical patent/CN112693474A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
    • G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
    • B60W50/0205—Diagnosing or detecting failures; Failure detection models
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/497—Means for monitoring or calibrating
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
    • G05B23/0283—Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL]
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/0055—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots with safety arrangements
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/0094—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots involving pointing a payload, e.g. camera, weapon, sensor, towards a fixed or moving target
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
    • G06V10/993—Evaluation of the quality of the acquired pattern
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0808—Diagnosing performance data
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Theoretical Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Multimedia (AREA)
  • Quality & Reliability (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Signal Processing (AREA)
  • Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Electromagnetism (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention relates to sensing system diagnostics using predicted sensor data and sensing results. A perception system comprising: a sensing module configured to capture first sensor data, the first sensor data comprising data from at least one of an external sensor and a camera captured during a first period of time; a prediction module configured to receive the first sensor data, generate predicted sensor data for a second time period after the first time period based on the first sensor data, receive second sensor data for the second time period, and output a result of a comparison between the predicted sensor data and the second sensor data; and a diagnostic module configured to selectively identify a fault in the sensing system based on a result of the comparison.

Description

Perception system diagnostics using predicted sensor data and perception results
Cross Reference to Related Applications
The present disclosure, according to subject matter, relates to U.S. patent application No. 16/527,561 filed on 31.7.2019 and U.S. patent application No. 16/541,421 filed on 15.8.2019. The entire disclosure of the above-referenced application is incorporated herein by reference.
Technical Field
The information provided in this section is for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in this section, as well as aspects of the description that may not otherwise qualify as prior art at the time of filing, are neither expressly nor impliedly admitted as prior art against the present disclosure.
The present disclosure relates to sensing systems for vehicles, and more particularly to systems and methods for diagnosing faults in sensing systems for vehicles.
Background
Vehicles include one or more torque-generative devices, such as an internal combustion engine and/or an electric motor. A passenger of the vehicle is seated in a passenger compartment (or passenger compartment) of the vehicle.
The vehicle may include one or more different types of sensors that sense the environment surrounding the vehicle. One example of a sensor that senses the vehicle surroundings is a camera configured to capture images of the vehicle surroundings. Examples of such cameras include forward-facing cameras, rearward-facing cameras, and side-facing cameras. Another example of a sensor that senses the vehicle surroundings includes a radar sensor configured to capture information about the vehicle surroundings. Other examples of sensors that sense the vehicle surroundings include sonar sensors and light detection and ranging (LIDAR) sensors, which are configured to capture information about the vehicle surroundings.
Disclosure of Invention
A perception system comprising: a sensing module configured to capture first sensor data, the first sensor data comprising data from at least one of an external sensor and a camera captured during a first period of time; a prediction module configured to receive first sensor data, generate predicted sensor data for a second period of time after the first period of time based on the first sensor data, receive second sensor data for the second period of time, and output a result of a comparison between the predicted sensor data and the second sensor data; and a diagnostic module configured to selectively identify a fault in the sensing system based on a result of the comparison.
In other features, the first sensor data further comprises historical sensor data captured in a period prior to the first period.
In other features, the prediction module is configured to generate the predicted sensor data further based on historical sensor data.
In other features, the result of the comparison includes a numerical representation of a difference between the predicted sensor data and the second sensor data.
In other features, the prediction module includes a convolutional long-and-short memory network.
In other features, the perception module is further configured to generate a perception result based on the second sensor data, wherein the perception result identifies a feature included in the second sensor data.
In other features, the prediction module is configured to generate a predicted perception result, the predicted perception result corresponding to the predicted sensor data.
In other features, the prediction module is configured to compare the predicted perception result with the perception result and provide a result of the comparison between the predicted perception result and the perception result to the diagnostic module.
In other features, the diagnostic module is configured to selectively identify the fault in the perception system further based on a result of the comparison between the predicted perception result and the perception result.
In other features, the failure corresponds to a failure of at least one of an external sensor and a camera.
A method of operating a perception system comprising: capturing first sensor data, wherein the first sensor data comprises data from at least one of an external sensor and a camera captured during a first period of time; generating predicted sensor data for a second time period after the first time period based on the first sensor data; receiving second sensor data for a second time period; outputting a result of a comparison between the predicted sensor data and the second sensor data; and selectively identifying a fault in the perception system based on a result of the comparison.
In other features, the first sensor data further comprises historical sensor data captured in a period prior to the first period.
In other features, the method comprises: predicted sensor data is generated further based on the historical sensor data.
In other features, the result of the comparison includes a numerical representation of a difference between the predicted sensor data and the second sensor data.
In other features, the method comprises: the predicted sensor data is generated using a convolutional long-term memory network.
In other features, the method comprises: a perception result is generated based on the second sensor data, wherein the perception result identifies a feature included in the second sensor data.
In other features, the method comprises: generating a predicted perception result, the predicted perception result corresponding to the predicted sensor data.
In other features, the method comprises: the predicted perception result is compared to the perception result and the fault in the perception system is selectively identified further based on the result of the comparison between the predicted perception result and the perception result.
In other features, the failure corresponds to a failure of at least one of an external sensor and a camera.
A perception system for a vehicle comprising: at least one of an external sensor and a camera arranged to provide data corresponding to an environment surrounding the vehicle; a sensing module configured to: capturing first sensor data, the first sensor data comprising data from at least one of an external sensor and a camera captured during a first period of time; capturing second sensor data including data from at least one of an external sensor and a camera captured in a second time period after the first time period; and generating a perception result based on the second sensor data, the perception result identifying a feature included in the second sensor data. The sensing system further comprises: a prediction module configured to: receiving first sensor data, second sensor data and a sensing result; generating predicted sensor data for a second time period based on the first sensor data; generating a predicted perception result based on the predicted sensor data; and outputting a result of a first comparison between the predicted sensor data and the second sensor data and a second comparison between the predicted sensing result and the sensing result; and a diagnostic module configured to selectively identify a fault in the perception system based on results of the first and second comparisons.
The invention provides the following technical scheme:
1. a perception system, comprising:
a sensing module configured to capture first sensor data, wherein the first sensor data comprises data from at least one of an external sensor and a camera captured over a first period of time;
a prediction module configured to: (i) receiving the first sensor data; (ii) generating predicted sensor data for a second time period after the first time period based on the first sensor data; (iii) receiving second sensor data for the second time period; and (iv) outputting a result of the comparison between the predicted sensor data and the second sensor data; and
a diagnostic module configured to selectively identify a fault in the perception system based on a result of the comparison.
2. The perception system of claim 1, wherein the first sensor data further comprises historical sensor data captured in a period prior to the first period.
3. The perception system of claim 2, wherein the prediction module is configured to generate the predicted sensor data further based on the historical sensor data.
4. The perception system of claim 1, wherein the result of the comparison includes a numerical representation of a difference between the predicted sensor data and the second sensor data.
5. The perception system of claim 1, wherein the prediction module comprises a convolutional long-and-short memory network.
6. The perception system of claim 1, wherein the perception module is further configured to generate a perception result based on the second sensor data, wherein the perception result identifies a feature included in the second sensor data.
7. The perception system of claim 6, wherein the prediction module is configured to generate a predicted perception result, the predicted perception result corresponding to the predicted sensor data.
8. The perception system of claim 7, wherein the prediction module is configured to: (i) comparing the predicted perception result with the perception result; and (ii) providing the results of the comparison between the predicted perception result and the perception result to the diagnostic module.
9. The perception system of claim 8, wherein the diagnostic module is configured to selectively identify a fault in the perception system further based on the result of the comparison between the predicted perception result and the perception result.
10. The perception system of claim 1, wherein the failure corresponds to a failure of at least one of the external sensor and the camera.
11. A method of operating a perception system, the method comprising:
capturing first sensor data, wherein the first sensor data comprises data from at least one of an external sensor and a camera captured over a first period of time;
generating predicted sensor data for a second time period after the first time period based on the first sensor data;
receiving second sensor data for the second time period;
outputting a result of a comparison between the predicted sensor data and the second sensor data; and
selectively identifying a fault in the perception system based on a result of the comparison.
12. The method of claim 11, wherein the first sensor data further comprises historical sensor data captured in a period prior to the first period.
13. The method of aspect 12, further comprising: generating the predicted sensor data further based on the historical sensor data.
14. The method of claim 11, wherein the result of the comparison comprises a numerical representation of a difference between the predicted sensor data and the second sensor data.
15. The method of scheme 11, further comprising: generating the predicted sensor data using a convolutional long-term memory network.
16. The method of scheme 11, further comprising: generating a perception result based on the second sensor data, wherein the perception result identifies a feature included in the second sensor data.
17. The method of aspect 16, further comprising: generating a predicted perception result, the predicted perception result corresponding to the predicted sensor data.
18. The method of scheme 17, further comprising: comparing the predicted perception result with the perception result and further selectively identifying a fault in the perception system based on a result of the comparison between the predicted perception result and the perception result.
19. The method of claim 11, wherein the failure corresponds to a failure of at least one of the external sensor and the camera.
20. A perception system for a vehicle, the perception system comprising:
at least one of an external sensor and a camera arranged to provide data corresponding to an environment surrounding the vehicle;
a sensing module configured to:
capturing first sensor data, wherein the first sensor data comprises data from at least one of the external sensor and the camera captured over a first period of time,
capturing second sensor data, wherein the second sensor data comprises data from at least one of the external sensor and the camera captured in a second period of time after the first period of time, an
Generating a perception result based on the second sensor data, wherein the perception result identifies a feature included in the second sensor data;
a prediction module configured to: (i) receiving the first sensor data, the second sensor data, and the perception result; (ii) generating predicted sensor data for the second time period based on the first sensor data; (iii) generating a predicted perception result based on the predicted sensor data; and (iv) outputting a result of a first comparison between the predicted sensor data and the second sensor data and a second comparison between the predicted perception result and the perception result; and
a diagnostic module configured to selectively identify a fault in the perception system based on the results of the first and second comparisons.
Further areas of applicability of the present disclosure will become apparent from the detailed description, claims, and drawings. The detailed description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure.
Drawings
The present disclosure will become more fully understood from the detailed description and the accompanying drawings, wherein:
FIG. 1 is a functional block diagram of an example vehicle system;
FIG. 2 is a functional block diagram of a vehicle including various external cameras and sensors;
FIG. 3 is a functional block diagram of an example implementation of a perception module and a diagnostic module;
FIG. 4 is a functional block diagram of an example prediction module;
FIG. 5 is a functional block diagram of an example sensor data prediction module; and
FIG. 6 illustrates steps of an example method of diagnosing a fault associated with a perception system of a vehicle.
In the drawings, reference numbers may be reused to identify similar and/or identical elements.
Detailed Description
The vehicle may include a perception system that perceives objects located around the vehicle based on data from external cameras and sensors. Examples of the exterior camera include a forward-facing camera, a backward-facing camera, and a side-facing camera. External sensors include radar sensors, light detection and ranging (LIDAR) sensors, and other types of sensors.
A prediction module and a diagnostic module according to the principles of the present disclosure are respectively configured to predict sensor data and a sensing outcome and selectively diagnose a fault associated with a sensing system of a vehicle based on a comparison of the predicted sensor data and actual sensor data and a comparison of the predicted sensing outcome and actual sensing outcome. The predicted sensor data and the perception result may be based on historical sensor data. For example, neural networks may use historical raw data to predict sensor data and perception outcomes.
Referring now to FIG. 1, a functional block diagram of an example vehicle system 100 is presented. Although the vehicle system 100 for a hybrid vehicle is shown and will be described, the present disclosure is also applicable to non-hybrid vehicles, electric vehicles, fuel cell vehicles, autonomous vehicles, and other types of vehicles. Also, while a vehicle example is provided, the present application is also applicable to non-vehicle embodiments.
The engine 102 may combust an air/fuel mixture to generate drive torque. An Engine Control Module (ECM) 106 controls the engine 102. For example, the ECM 106 may control actuation of engine actuators, such as a throttle valve, one or more spark plugs, one or more fuel injectors, valve actuators, camshaft phasers, Exhaust Gas Recirculation (EGR) valves, one or more boost devices, and other suitable engine actuators. In some types of vehicles (e.g., electric vehicles), the engine 102 may be omitted.
The engine 102 may output torque to the transmission 110. A Transmission Control Module (TCM) 114 controls operation of the transmission 110. For example, the TCM 114 may control gear selection within the transmission 110 and one or more torque-transfer devices (e.g., torque converters, one or more clutches, etc.).
The vehicle system 100 may include one or more electric motors. For example, the electric motor 118 may be implemented within the transmission 110, as shown in the example of fig. 1. An electric motor may act as either a generator or a motor at a given time. When acting as a generator, the electric motor converts mechanical energy into electrical energy. The electrical energy may be used, for example, to charge a battery 126 via a Power Control Device (PCD) 130. When acting as a motor, the electric motor generates torque that may be used, for example, to supplement or replace the torque output by the engine 102. Although an example of one electric motor is provided, the vehicle may include zero or more than one electric motor.
A power inverter control module (PIM) 134 may control the electric motor 118 and the PCD 130. The PCD 130 applies power from the battery 126 to the electric motor 118 based on the signal from the PIM 134, and the PCD 130 provides power output by the electric motor 118, for example, to the battery 126. In various implementations, the PIM 134 may be referred to as a Power Inverter Module (PIM).
The steering control module 140 controls steering/turning of the wheels of the vehicle, for example, based on driver turns of a steering wheel within the vehicle and/or steering commands from one or more vehicle control modules. A steering wheel angle Sensor (SWA) monitors the rotational position of the steering wheel and generates a SWA 142 based on the position of the steering wheel. As an example, the steering control module 140 may control vehicle steering via the EPS motor 144 based on the SWA 142. However, the vehicle may include another type of steering system.
An Electronic Brake Control Module (EBCM) 150 may selectively control the brakes 154 of the vehicle. The modules of the vehicle may share parameters via a Controller Area Network (CAN) 162. CAN162 may also be referred to as an automotive lan. For example, CAN162 may include one or more data buses. Various parameters may be provided by a given control module to other control modules via CAN 162.
The driver inputs may include, for example, an Accelerator Pedal Position (APP) 166 that may be provided to the ECM 106. A Brake Pedal Position (BPP) 170 may be provided to the EBCM 150. A park, reverse, neutral, drive rod (PRNDL) position 174 may be provided to the TCM 114. The ignition status 178 may be provided to a Body Control Module (BCM) 180. For example, the ignition status 178 may be entered by the driver via an ignition key, button, or switch. At a given time, the ignition state 178 may be one of off, accessory, run, or start.
The vehicle system 100 may also include an infotainment module 182. The infotainment module 182 controls the content displayed on the display 184. In various implementations, the display 184 may be a touch screen display and signals indicative of user inputs to the display 184 are transmitted to the infotainment module 182. The infotainment module 182 may additionally or alternatively receive signals indicative of user input from one or more other user input devices 185, such as one or more switches, buttons, knobs, etc. The infotainment module 182 may also generate output via one or more other devices. For example, the infotainment module 182 may output sound via one or more speakers 190 of the vehicle.
The vehicle may include a plurality of external sensors and cameras, generally illustrated in FIG. 1 by 186. One or more actions may be taken based on input from external sensors and the camera 186. For example, the infotainment module 182 may display video, various views, and/or alerts on the display 184 via input from external sensors and cameras 186.
As another example, based on input from external sensors and the camera 186, the perception module 196 perceives objects around the vehicle and the position of the objects relative to the vehicle. The ECM 106 may adjust a torque output of the engine 102 based on input from the sensing module 196. Additionally or alternatively, the PIM 134 may control power flow to and/or from the electric motor 118 based on input from the perception module 196. Additionally or alternatively, EBCM 150 may adjust braking based on input from sensing module 196. Additionally or alternatively, the steering control module 140 may adjust steering based on input from the perception module 196. The vehicle system 100 according to the principles of the present disclosure is configured to predict sensor data and sensing results and perform diagnostics based on a comparison between the predicted sensor data and sensing results and actual sensor data and sensing results, as described in more detail below.
The vehicle may include one or more additional control modules, not shown, such as a chassis control module, a battery pack control module, and the like. The vehicle may omit one or more of the control modules shown and discussed.
Referring now to fig. 2, a functional block diagram of a vehicle 200 implementing the vehicle system 100 of fig. 1 and including examples of external sensors and cameras (e.g., corresponding to the external sensors and cameras 186 as described above in fig. 1) is presented. External sensors and cameras 186 include various cameras positioned to capture images and video outside of vehicle 200 (outside of vehicle 200), and various types of sensors that measure parameters outside of vehicle 200 (outside of vehicle 200). For example, forward-facing camera 204 captures images and video of images within a predetermined field of view (FOV) 206 in front of vehicle 200.
Front-facing camera 208 may also capture images and video within a predetermined FOV 210 in front of vehicle 200. Front-facing camera 208 may capture images and video within a predetermined distance in front of vehicle 200, and may be located in front of vehicle 200 (e.g., in a front fascia, grille, or bumper). However, the forward-facing camera 204 may be located further rearward, such as where a rear-view mirror is present at the windshield of the vehicle 200. Forward-facing camera 204 may be unable to capture images and video of items within all or at least a portion of the predetermined FOV of front-facing camera 208 and may capture images and video greater than a predetermined distance forward of vehicle 200. In various embodiments, only one of the forward-facing camera 204 and the front-facing camera 208 may be included.
The rear camera 212 captures images and video within a predetermined FOV 214 behind the vehicle 200. The rear camera 212 may capture images and video within a predetermined distance behind the vehicle 200 and may be located at the rear of the vehicle 200, such as near the rear license plate.
The right camera 216 captures images and video within a predetermined FOV 218 on the right side of the vehicle 200. The right camera 216 may capture images and video within a predetermined distance of the right side of the vehicle 200 and may be located, for example, below the right side rearview mirror. In various embodiments, the right side rearview mirror may be omitted, and the right camera 216 may be located near where the right side rearview mirror would normally be.
The left camera 220 captures images and video within a predetermined FOV 222 on the left side of the vehicle 200. Left camera 220 may capture images and video within a predetermined distance of the left side of vehicle 200 and may be located, for example, below the left side rear view mirror. In various embodiments, the left side mirror may be omitted, and the left camera 220 may be located near where the left side mirror would normally be. Although example FOVs are shown for illustrative purposes, these FOVs may overlap, for example, for more accurate and/or inclusive stitching.
The external sensors and cameras 186 may additionally or alternatively include various other types of sensors, such as ultrasonic (e.g., radar) sensors. For example, the vehicle 200 may include one or more forward ultrasonic sensors (such as forward ultrasonic sensors 226 and 230), one or more rearward ultrasonic sensors (such as rearward ultrasonic sensors 234 and 238). The vehicle 200 may also include one or more right side ultrasonic sensors (such as the right side ultrasonic sensor 242) and one or more left side ultrasonic sensors (such as the left side ultrasonic sensor 246). The locations of the camera and the ultrasonic sensor are provided as examples only, and different locations may be used. The ultrasonic sensor outputs an ultrasonic signal around the vehicle 200.
The external sensors and cameras 186 may additionally or alternatively include one or more other types of sensors, such as one or more sonar sensors, one or more radar sensors, and/or one or more light detection and ranging (LIDAR) sensors.
Fig. 3 is a functional block diagram of an example implementation of a perception system 300 according to the principles of the present disclosure. The perception system 300 includes a perception module 196, a prediction module 304, and a diagnostic module 308. The diagnostic module 308 selectively diagnoses faults associated with the sensing module 196 and the external sensors and cameras 186.
The perception module 196 includes a snapshot module 312 configured to capture a snapshot 316 of data (e.g., sensor data) including data from one of the external sensor and the camera 186. The snapshot module 312 may capture new snapshots every predetermined period of time. The snapshot 316 may include a forward image 320 captured using the forward camera 204, a time 324 (and date; e.g., a timestamp) at which the forward image 320 was captured, and a location 328 of the vehicle 200 at the time the forward image 320 was captured. Although an example of a snapshot 316 including a forward image 320 will be discussed, the present application is also applicable to data from external sensors and other ones of the cameras 186. The clock may track and provide a (current) time 324. A Global Positioning System (GPS) may track and provide a (current) location 328. Snapshots may be obtained and the following operations may be performed for each of the external sensors and cameras 186.
The feature extraction module 332 identifies features and feature locations 336 in the forward image 320 of the snapshot 316. Examples of features include, for example, edges of objects, shapes of objects, and the like. The feature extraction module 332 may use one or more feature extraction algorithms, such as a Scale Invariant Feature Transform (SIFT) algorithm, an Speeded Up Robust Features (SURF) algorithm, and/or one or more other feature extraction algorithms, to identify features and locations.
The object module 340 labels objects in the forward image 320 of the snapshot 316 based on features identified in the forward image 320 of the snapshot 316. For example, the object module 340 may identify shapes in the forward image 320 based on the shapes of the identified features and match those shapes to predetermined shapes of objects stored in a database. The object module 340 may assign a name or code word of a predetermined shape matching the shape to the shape of the identified feature. The object module 340 outputs the perception results, such as the marked object and the location 344. As another example, the deep neural network module may implement the functionality of both the feature extraction module 332 and the object module 340. The first few layers in such a deep neural network module perform the function of feature extraction and then pass the features to the remaining layers in the deep neural network module to perform the function of object labeling. The vehicle may have more than one feature extraction module independent of each other.
One or more actions may be taken based on the marked object and the location 344. For example, the infotainment module 182 may display a video, various views, and/or an alert on the display 184. As another example, the ECM 106 may adjust the torque output of the engine 102 based on the tagged object and the position 344. Additionally or alternatively, the PIM 134 may control power flow to and/or from the electric motor 118 based on the marked object and the position 344. Additionally or alternatively, the EBCM 150 may adjust braking based on the marked object and the location 344. Additionally or alternatively, the steering control module 140 may adjust the steering based on the marked object and the position 344.
Prediction module 304 also receives sensor data (e.g., snapshot 316) and sensing results (e.g., tagged object and location 344) from sensing module 196 for the first time period. The prediction module 304 is configured to predict the sensor data and the perceived result for the second time period (which may be referred to as a predicted current or next frame of data, for example) and compare the predicted sensor data and the perceived result for the second time period to the actual sensor data and the perceived result. The diagnostic module 308 is configured to perform diagnostics based on a comparison between predicted sensor data and sensory results and actual sensor data and sensory results, as described in more detail below.
All or part of the prediction module 304 and the diagnostic module 308 may be implemented within the vehicle 200. Alternatively, all or part of the prediction module 304 and the diagnosis module 308 may be remotely located, such as in a remote server or cloud computing system. If all or part of the prediction module 304 and the diagnostic module 308 are remotely located, the vehicle 200 may include one or more transceivers that wirelessly transmit data to and from the vehicle 200, such as via a cellular transceiver, a WiFi transceiver, a satellite transceiver, and/or another suitable type of wireless communication.
Referring now to FIG. 4, the prediction module 304 is shown in greater detail. Prediction module 304 includes a sensor data prediction module 400 configured to receive data including current sensor data (D)k) And historical sensor data (D)k-1、Dk-2Etc.), where k identifies a time period corresponding to the capture of the sensor data. Upon reception of current sensor data DkThereafter, the sensor data prediction module 400 also receives the next sensor data Dk+1. In other words, the sensor data includes a plurality of captured frames or snapshots of the sensor data. The current sensor data corresponds to the actual sensor data captured. In some examples, the sensor data prediction module 400 may be configured to store historical sensor data and/or retrieve historical sensor data from a storage location (e.g., a buffer, a remote server, etc.).
Sensor data prediction module 400 bases on historical sensor data (e.g., D)k-1、Dk-2、Dk-3Etc. which correspond to D in the previous periodkBuffered samples of) output predicted sensor data (D'k). For example, the sensor data prediction module 400 calculates predicted sensor data based on one or more frames of historical sensor data, as described in more detail in fig. 5. The predicted sensor data corresponds to the latest historical frame of sensor data (e.g., D)k-1) The predicted sensor data thereafter. Sensor data comparison module 404 receives and compares predicted sensor data D'kAnd actual current sensor data DkAnd outputs the comparison results accordingly (e.g., to the diagnostic module 308). For example, the comparison result corresponds to predicted sensor data D'kAnd actual sensingDevice data DkThe numerical representation of the difference between.
The predicted sensor data is also provided to the feature extraction module 408. For example, the feature extraction module 408 may be configured similar to the feature extraction module 332 and identify features and locations of features indicated in the predicted sensor data. Similarly, object module 412 (e.g., constructed in a similar manner as object module 340) labels objects indicated in the predicted sensor data based on the features identified by feature extraction module 408. In this manner, object module 412 outputs a predicted perceptual result R'k。
Perceptual result comparison module 416 receives and compares predicted perceptual results R'kAnd the actual sensing result RkAnd outputs the comparison results accordingly (e.g., to the diagnostic module 308). In other words, predicted perceptual result R'kCorresponding to the predicted result as calculated from the predicted sensor data. In contrast, the actual sensing result RkCorresponding to the actual predicted outcome as calculated for the actual sensor data at the same time period. Thus, the comparison result output by the perception result comparison module 416 corresponds to a difference between the perception result calculated for the actual sensor data and the perception result calculated for the predicted sensor data. For example, the comparison result corresponds to a predicted perceptual result R'kAnd the actual sensing result RkThe numerical representation of the difference between.
Referring now to FIG. 5, the sensor data prediction module 400 is shown in greater detail. The sensor data prediction module 400 includes a neural or machine learning network, such as a convolutional long term memory (LSTM) network 500 that includes a plurality of Convolutional Neural Network (CNN) layers. For example, convolutional LSTM network 500 includes an encoder section 504 and a decoder section 508. Each of the encoder section 504 and the decoder section 508 includes a respective plurality of convolutional LSTM layers 512. For example only, each of the encoder section 504 and the decoder section 508 includes L convolutional LSTM layers 512, for a total of 2L convolutional LSTM layers 512.
Encoder section 504 (e.g., first convolution LSTM layer of encoder section 504)512) Receiving sensor data Dk-1(e.g., where k, k-1, etc. correspond to a time period or timestamp) as an input. For example, sensor data from the respective time period may be provided to a buffer 514, which in turn outputs the sensor data to the encoder section 504. Each of the convolved LSTM layers 512 of the encoder section 504 will output (d)k-1, 1...dk-1, L) To the next one in the convolutional LSTM layer 512. The last of the convolved LSTM layers 512 of the encoder section 504 will output dkL is provided to a first one of the convolutional LSTM layers 512 of the decoder section 508. Each of the convolutional LSTM layers 512 of the decoder section 508 will output (d)k-1, L+ 1...dk-1, 2L-1) To the next one in the convolutional LSTM layer 512. Each of the convolved LSTM layers 512 further receives a respective previous state(s) of the convolved LSTM layer 512k-2, 1…sk-2, 2L) And previous output (d)k-2, 1…dk-2, 2L). The last of the convolved LSTM layers 512 provides sensor data D 'corresponding to the prediction'kOutput d ofk-1, 2L. Predicted sensor data D'kCorresponding to the inclusion of sensor data Dk-1The predicted frame of sensor data after the frame of (a).
The sensor data prediction module 400 may include a loss function module 516. Loss function module 516 receives and compares predicted sensor data D'kAnd the actual current sensor data frame Dk. Loss function module 516 outputs predicted sensor data D'kAnd the actual current sensor data frame DkComparison (e.g., predicted sensor data D'kAnd the actual current sensor data frame DkThe difference or distance between) of the two. For example, the output of loss function module 516 may correspond to predicted sensor data D'kAnd the actual current sensor data frame DkMean square error between. For example only, the output of the loss function module 516 may be based on
Figure DEST_PATH_IMAGE002
To indicate a loss L. The output of the penalty function block 516 is availableIn training the convolutional LSTM network 500.
Referring now to FIG. 6, an example method 600 of diagnosing a fault associated with a perception system of a vehicle begins at 604. For example, the method 600 is implemented using the prediction module 304 and the diagnostic module 308, as described above. At 608, the method 600 (e.g., the diagnostic module 308) receives predicted sensor data (e.g., D'k) And predicted perceptual results (e.g., R'k) And actual sensor data (e.g., D)k) And actual perceived result (e.g., R)k). At 612, the method 600 (e.g., the diagnostic module 308) determines predicted sensor data D'kAnd actual sensor data DkDifference (e.g., Δ) betweend, k) Whether greater than or equal to a first threshold. If true, method 600 continues to 616. If false, method 600 continues to 620. At 616, the method 600 (e.g., the diagnostic module 308) stores and/or outputs an indication that the first fault type has been detected in the sensing system. For example, the first fault type indicates that a sensor associated with the sensor data is faulty. The method 600 then ends at 624.
At 620, the method 600 (e.g., the diagnostic module 308) determines predicted sensor data D'kAnd actual sensor data DkWhether the difference between is less than a second threshold value, which is less than the first threshold value. If true, method 600 continues to 628. If false, method 600 continues to 632. At 632, the method 600 (e.g., the diagnostic module 308) stores and/or outputs an indication that a second fault type has been detected in the sensing system. For example, the second fault type indicates: while the sensor may not be malfunctioning, the sensor data results may not be as accurate as desired. In other words, though predicted sensor data D'kAnd actual sensor data DkThe difference between is not greater than or equal to the first threshold, but the difference is still greater than desired. The method 600 then ends at 624.
At 628, the method 600 (e.g., the diagnostic module 300) determines: (i) predicted perceptual result R'kFirst ofWhether the error measurement is greater than or equal to a third threshold; and (ii) a predicted perceptual result R'kIs greater than or equal to a fourth threshold. For example, the first and second error measurements may be based on a predicted perceptual result R'kAnd the actual sensing result RkA comparison between them. In one example, the first error measure corresponds to a false positive rate (i.e., at predicted perceptual result R'kIs indicated in (b), but at the actual sensing result RkThe detection rate of undetected objects). Conversely, the second error measure corresponds to a false negative rate (i.e., at the predicted perceptual result R'kWith respect to the actual sensing result RkThe ratio of detected objects). If either of (i) and (ii) is true, method 600 continues to 636. If both (i) and (ii) are not true, method 600 continues to 640.
At 636, the method 600 (e.g., the diagnostic module 308) stores and/or outputs an indication that a third fault type has been detected in the sensing system. For example, the third fault type indicates that there is a fault in the calculation of the perception result (e.g., a fault in software associated with the feature extraction module 332 and/or the object module 340). The method 600 then ends at 624.
At 640, the method 600 (e.g., the diagnostic module 300) determines: (i) whether the first error measurement is less than a fifth threshold, the fifth threshold being less than a third threshold; and (ii) whether the second error measurement is less than a sixth threshold, the sixth threshold being less than a fourth threshold. If both (i) and (ii) are true, method 600 continues to 644. If neither of (i) and (ii) are true, method 600 continues to 648. At 648, the method 600 (e.g., the diagnostic module 308) stores and/or outputs an indication that the second fault type has been detected in the sensing system. For example, the second fault type indicates: while the sensor may not be faulty and the sensing results are relatively accurate, the sensing results may not be as accurate as desired. The method 600 then ends at 624.
At 644, the method 600 (e.g., the diagnostic module 308) stores and/or outputs an indication that the sensing system is free of any faults and that the prediction and sensing results are accurate, and then ends at 624.
In some examples, method 600 may include one or more fault mitigation steps in response to determining that the perception system has a fault. For example, method 600 may include alerting the driver, disengaging autonomous vehicle control, driving the vehicle to the side of the road, continuing operation without using a sensor that is indicated as faulty, and so forth. In other words, because the sensing system relies on receiving accurate information and sensing results from the sensors, the detection of a fault in one or more of the sensors and/or the calculation of the sensing results may indicate that fault mitigation is necessary. Thus, fault mitigation may include one or more steps to limit or terminate the ability of the perception system to control the vehicle and return control to the driver.
The method 600 may be performed continuously, periodically (e.g., a predetermined amount of time after starting the vehicle), and/or conditionally, such as in response to the vehicle being in a predetermined location (e.g., each time the vehicle passes a particular intersection, passes near a predetermined building or structure, etc.).
The foregoing description is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses. The broad teachings of the disclosure can be implemented in a variety of forms. Therefore, while this disclosure includes particular examples, the true scope of the disclosure should not be so limited since other modifications will become apparent upon a study of the drawings, the specification, and the following claims. It should be understood that one or more steps within a method may be performed in a different order (or simultaneously) without altering the principles of the present disclosure. Further, while each of the embodiments is described above as having certain features, any one or more of those features described with respect to any embodiment of the disclosure may be implemented in any of the other embodiments and/or combined with the features of any of the other embodiments, even if the combination is not explicitly described. In other words, the described embodiments are not mutually exclusive and combinations of one or more of the embodiments with each other are still within the scope of the disclosure.
The spatial and functional relationships between various elements (e.g., between modules, circuit elements, semiconductor layers, etc.) are described using various terms, including "connected," joined, "" coupled, "" adjacent, "" immediately adjacent, "" on top of … …, "" above, "" below, "and" disposed. Unless explicitly described as "direct", when a relationship between a first element and a second element is described in the above disclosure, the relationship may be a direct relationship in which no other intervening element exists between the first element and the second element, but may also be an indirect relationship in which one or more intervening elements exist (spatially or functionally) between the first element and the second element. As used herein, at least one of the phrases A, B and C should be interpreted to mean using a non-exclusive logical OR to represent a logical (a OR B OR C), and should not be interpreted to mean "at least one of a, at least one of B, and at least one of C".
In the drawings, the direction of arrows as indicated by the arrows generally represent the flow of information (such as data or instructions) of interest as illustrated. For example, when element a and element B exchange various information but the information transmitted from element a to element B is related to the illustration, the arrow may point from element a to element B. Such a one-way arrow does not imply that no other information is transferred from element B to element a. Further, for information sent from element a to element B, element B may send a request for information or an acknowledgement of receipt of the information to element a.
In this application (including the definitions below), the term "module" or the term "controller" may be replaced with the term "circuit". The term "module" may refer to, be part of, or include: an Application Specific Integrated Circuit (ASIC); digital, analog, or hybrid analog/digital discrete circuits; digital, analog, or hybrid analog/digital integrated circuits; a combinational logic circuit; a Field Programmable Gate Array (FPGA); processor circuitry (shared, dedicated, or group) that executes code; memory circuitry (shared, dedicated, or group) that stores code executed by the processor circuitry; other suitable hardware components that provide the described functionality; or a combination of some or all of the above, such as in a system on a chip.
The module may include one or more interface circuits. In some examples, the interface circuit may include a wired or wireless interface to a Local Area Network (LAN), the internet, a Wide Area Network (WAN), or a combination thereof. The functionality of any given module of the present disclosure may be distributed among multiple modules connected via interface circuits. For example, multiple modules may allow load balancing. In further examples, a server (also referred to as a remote or cloud) module may perform some function on behalf of a client module.
The term code, as used above, may include software, firmware, and/or microcode, and may refer to programs, routines, functions, classes, data structures, and/or objects. The term shared processor circuit encompasses a single processor circuit that executes some or all code from multiple modules. The term group processor circuit encompasses a processor circuit that, in combination with additional processor circuits, executes some or all code from one or more modules. References to multiple processor circuits encompass multiple processor circuits on separate dies, multiple processor circuits on a single die, multiple cores of a single processor circuit, multiple threads of a single processor circuit, or a combination of the foregoing. The term shared memory circuit encompasses a single memory circuit that stores some or all code from multiple modules. The term bank memory circuit encompasses memory circuits that, in combination with additional memory, store some or all code from one or more modules.
The term memory circuit is a subset of the term computer readable medium. The term computer-readable medium as used herein does not encompass transitory electrical or electromagnetic signals propagating through a medium (such as on a carrier wave); thus, the term computer-readable medium may be considered tangible and non-transitory. Non-limiting examples of a non-transitory, tangible computer-readable medium are a non-volatile memory circuit (such as a flash memory circuit, an erasable programmable read-only memory circuit, or a mask read-only memory circuit), a volatile memory circuit (such as a static random access memory circuit or a dynamic random access memory circuit), a magnetic storage medium (such as an analog or digital tape or hard drive), and an optical storage medium (such as a CD, DVD, or blu-ray disc).
The apparatus and methods described herein may be partially or wholly implemented by a special purpose computer created by causing a general purpose computing mechanism to perform one or more specific functions embodied in a computer program. The functional blocks, flowchart components and other elements described above are used as software specifications, which can be transformed into a computer program by routine work of a skilled technician or programmer.
The computer program includes processor-executable instructions stored on at least one non-transitory, tangible computer-readable medium. The computer program may also comprise or rely on stored data. A computer program can encompass a basic input/output system (BIOS) that interacts with the hardware of a special purpose computer, a device driver that interacts with specific devices of a special purpose computer, one or more operating systems, user applications, background services, background applications, and the like.
The computer program may include: (i) descriptive text to be parsed, such as HTML (hypertext markup language), XML (extensible markup language), or JSON (JavaScript object notation), (ii) assembly code, (iii) object code generated by a compiler from source code, (iv) source code executed by an interpreter, (v) source code compiled and executed by a just-in-time compiler, and so forth. By way of example only, the source code may be written using syntactic rules in languages including C, C + +, C #, Objective-C, Swift, Haskell, Go, SQL, R, Lisp, Java, Fortran, Perl, Pascal, Curl, OCamyl, Javascript, HTML5 (HyperText markup language version 5), Ada, ASP (dynamic Server Page), PHP (PHP: HyperText Pre-processing language), Scala, Eiffel, Smalltalk, Erlang, Ruby, Flash, Visual Basic, Lua, MATLAB, SIMULINK, and Python.

Claims (10)

1. A perception system, comprising:
a sensing module configured to capture first sensor data, wherein the first sensor data comprises data from at least one of an external sensor and a camera captured over a first period of time;
a prediction module configured to: (i) receiving the first sensor data; (ii) generating predicted sensor data for a second time period after the first time period based on the first sensor data; (iii) receiving second sensor data for the second time period; and (iv) outputting a result of the comparison between the predicted sensor data and the second sensor data; and
a diagnostic module configured to selectively identify a fault in the perception system based on a result of the comparison.
2. The perception system of claim 1, wherein the first sensor data further comprises historical sensor data captured in a period prior to the first period.
3. The perception system of claim 2, wherein the prediction module is configured to generate the predicted sensor data further based on the historical sensor data.
4. The perception system of claim 1, wherein the result of the comparison includes a numerical representation of a difference between the predicted sensor data and the second sensor data.
5. The perception system of claim 1, wherein the prediction module comprises a convolutional long-and-short memory network.
6. The perception system of claim 1, wherein the perception module is further configured to generate a perception result based on the second sensor data, wherein the perception result identifies a feature included in the second sensor data.
7. The perception system of claim 6, wherein the prediction module is configured to generate a predicted perception result, the predicted perception result corresponding to the predicted sensor data.
8. The perception system of claim 7, wherein the prediction module is configured to: (i) comparing the predicted perception result with the perception result; and (ii) providing the results of the comparison between the predicted perception result and the perception result to the diagnostic module.
9. The perception system of claim 8, wherein the diagnostic module is configured to selectively identify a fault in the perception system further based on the result of the comparison between the predicted perception result and the perception result.
10. The perception system as claimed in claim 1, wherein the malfunction corresponds to a malfunction of at least one of the external sensor and the camera.
CN202011148960.4A 2019-10-23 2020-10-23 Perception system diagnostics using predicted sensor data and perception results Pending CN112693474A (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US16/661,126 US11829128B2 (en) 2019-10-23 2019-10-23 Perception system diagnosis using predicted sensor data and perception results
US16/661126 2019-10-23

Publications (1)

Publication Number Publication Date
CN112693474A true CN112693474A (en) 2021-04-23

Family

ID=75378995

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011148960.4A Pending CN112693474A (en) 2019-10-23 2020-10-23 Perception system diagnostics using predicted sensor data and perception results

Country Status (3)

Country Link
US (1) US11829128B2 (en)
CN (1) CN112693474A (en)
DE (1) DE102020125596A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113965565A (en) * 2021-09-14 2022-01-21 南京融才交通科技研究院有限公司 Internet of things networking method and system based on information age
WO2024012252A1 (en) * 2022-07-14 2024-01-18 维沃移动通信有限公司 Sensing processing method and apparatus, terminal, network side device, and readable storage medium

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3772854A1 (en) * 2019-08-08 2021-02-10 Thinkware Corporation Server and method for providing connected service
US11663860B2 (en) * 2019-10-25 2023-05-30 Toyota Research Institute, Inc. Dynamic and variable learning by determining and using most-trustworthy inputs
US11436876B2 (en) * 2019-11-01 2022-09-06 GM Global Technology Operations LLC Systems and methods for diagnosing perception systems of vehicles based on temporal continuity of sensor data
US20220226994A1 (en) * 2020-07-20 2022-07-21 Georgia Tech Research Corporation Heterogeneous graph attention networks for scalable multi-robot scheduling
CN113391622B (en) * 2021-06-22 2022-09-02 中国人民解放军国防科技大学 Spacecraft attitude system anomaly detection method using multivariate multistep prediction technology
US11924527B2 (en) * 2022-05-10 2024-03-05 GM Global Technology Operations LLC Optical sensor activation and fusion

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120083923A1 (en) * 2009-06-01 2012-04-05 Kosei Matsumoto Robot control system, robot control terminal, and robot control method
US20170169627A1 (en) * 2015-12-09 2017-06-15 Hyundai Motor Company Apparatus and method for failure diagnosis and calibration of sensors for advanced driver assistance systems
US9760806B1 (en) * 2016-05-11 2017-09-12 TCL Research America Inc. Method and system for vision-centric deep-learning-based road situation analysis
CN107628036A (en) * 2016-07-19 2018-01-26 通用汽车环球科技运作有限责任公司 The detection and reconstruction of sensor fault
US20180053102A1 (en) * 2016-08-16 2018-02-22 Toyota Jidosha Kabushiki Kaisha Individualized Adaptation of Driver Action Prediction Models
CN108466623A (en) * 2017-02-23 2018-08-31 通用汽车环球科技运作有限责任公司 For detecting the installation of the faulty sensors in vehicle to alleviate the system and method for danger associated with object detection
US20190064810A1 (en) * 2017-08-28 2019-02-28 GM Global Technology Operations LLC Method and apparatus for monitoring of an autonomous vehicle
CN109421739A (en) * 2017-08-28 2019-03-05 通用汽车环球科技运作有限责任公司 Method and apparatus for monitoring autonomous vehicle
US10282623B1 (en) * 2015-09-25 2019-05-07 Apple Inc. Depth perception sensor data processing
US20190236865A1 (en) * 2018-01-31 2019-08-01 Mentor Graphics Development (Deutschland) Gmbh Self-diagnosis of faults in an autonomous driving system

Family Cites Families (34)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3007019B2 (en) * 1995-04-07 2000-02-07 三菱電機株式会社 Traffic flow measurement device
US7099510B2 (en) 2000-11-29 2006-08-29 Hewlett-Packard Development Company, L.P. Method and system for object detection in digital images
US7508979B2 (en) 2003-11-21 2009-03-24 Siemens Corporate Research, Inc. System and method for detecting an occupant and head pose using stereo detectors
WO2006086051A2 (en) 2004-12-03 2006-08-17 Sarnoff Corporation Method and apparatus for tracking a movable object
IL169269A (en) * 2005-06-19 2012-08-30 Israel Aerospace Ind Ltd Method for automatically guiding an unmanned vehicle and computer readable media bearing a
US8803966B2 (en) 2008-04-24 2014-08-12 GM Global Technology Operations LLC Clear path detection using an example-based approach
US8913783B2 (en) 2009-10-29 2014-12-16 Sri International 3-D model based method for detecting and classifying vehicles in aerial imagery
US20150371109A1 (en) 2013-01-17 2015-12-24 Sensen Networks Pty Ltd Automated vehicle recognition
US20150102955A1 (en) * 2013-10-14 2015-04-16 GM Global Technology Operations LLC Measurement association in vehicles
US10279488B2 (en) 2014-01-17 2019-05-07 Knightscope, Inc. Autonomous data machines and systems
JP6246014B2 (en) * 2014-02-18 2017-12-13 クラリオン株式会社 Exterior recognition system, vehicle, and camera dirt detection method
KR101620449B1 (en) * 2014-06-26 2016-05-12 삼성전자 주식회사 Robot cleaner and method for controlling the same
US10412369B2 (en) 2015-07-31 2019-09-10 Dell Products, Lp Method and apparatus for compensating for camera error in a multi-camera stereo camera system
US10339390B2 (en) 2016-02-23 2019-07-02 Semiconductor Components Industries, Llc Methods and apparatus for an imaging system
US9739881B1 (en) 2016-03-24 2017-08-22 RFNAV, Inc. Low cost 3D radar imaging and 3D association method from low count linear arrays for all weather autonomous vehicle navigation
US10618673B2 (en) 2016-04-15 2020-04-14 Massachusetts Institute Of Technology Systems and methods for dynamic planning and operation of autonomous systems using image observation and information theory
JP6595401B2 (en) 2016-04-26 2019-10-23 株式会社Ｓｏｋｅｎ Display control device
US10739786B2 (en) 2016-07-01 2020-08-11 Uatc, Llc System and method for managing submaps for controlling autonomous vehicles
US10664722B1 (en) 2016-10-05 2020-05-26 Digimarc Corporation Image processing arrangements
JP6840530B2 (en) 2016-12-22 2021-03-10 東芝テック株式会社 Image processing device and image processing method
US10630962B2 (en) 2017-01-04 2020-04-21 Qualcomm Incorporated Systems and methods for object location
US10471829B2 (en) 2017-01-16 2019-11-12 Nio Usa, Inc. Self-destruct zone and autonomous vehicle navigation
US10216198B2 (en) * 2017-03-21 2019-02-26 The Boeing Company Methods and apparatus to perform observer-based control of a vehicle
CN107358596B (en) 2017-04-11 2020-09-18 阿里巴巴集团控股有限公司 Vehicle loss assessment method and device based on image, electronic equipment and system
US10650256B2 (en) 2017-04-18 2020-05-12 nuTonomy Inc. Automatically perceiving travel signals
US10373000B2 (en) 2017-08-15 2019-08-06 GM Global Technology Operations LLC Method of classifying a condition of a road surface
US10713570B1 (en) 2017-10-04 2020-07-14 Diveplane Corporation Evolutionary programming techniques utilizing context indications
US10606274B2 (en) 2017-10-30 2020-03-31 Nio Usa, Inc. Visual place recognition based self-localization for autonomous vehicles
US10809064B2 (en) 2018-02-08 2020-10-20 Raytheon Company Image geo-registration for absolute navigation aiding using uncertainy information from the on-board navigation system
US10684626B1 (en) 2018-04-05 2020-06-16 Ambarella International Lp Handling intersection navigation without traffic lights using computer vision
KR20200029785A (en) 2018-09-11 2020-03-19 삼성전자주식회사 Localization method and apparatus of displaying virtual object in augmented reality
US11093560B2 (en) 2018-09-21 2021-08-17 Microsoft Technology Licensing, Llc Stacked cross-modal matching
KR20200046437A (en) 2018-10-24 2020-05-07 삼성전자주식회사 Localization method based on images and map data and apparatus thereof
WO2021006366A1 (en) 2019-07-05 2021-01-14 엘지전자 주식회사 Artificial intelligence device for adjusting color of display panel, and method therefor

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120083923A1 (en) * 2009-06-01 2012-04-05 Kosei Matsumoto Robot control system, robot control terminal, and robot control method
US10282623B1 (en) * 2015-09-25 2019-05-07 Apple Inc. Depth perception sensor data processing
US20170169627A1 (en) * 2015-12-09 2017-06-15 Hyundai Motor Company Apparatus and method for failure diagnosis and calibration of sensors for advanced driver assistance systems
US9760806B1 (en) * 2016-05-11 2017-09-12 TCL Research America Inc. Method and system for vision-centric deep-learning-based road situation analysis
CN107628036A (en) * 2016-07-19 2018-01-26 通用汽车环球科技运作有限责任公司 The detection and reconstruction of sensor fault
US20180053102A1 (en) * 2016-08-16 2018-02-22 Toyota Jidosha Kabushiki Kaisha Individualized Adaptation of Driver Action Prediction Models
CN108466623A (en) * 2017-02-23 2018-08-31 通用汽车环球科技运作有限责任公司 For detecting the installation of the faulty sensors in vehicle to alleviate the system and method for danger associated with object detection
US20190064810A1 (en) * 2017-08-28 2019-02-28 GM Global Technology Operations LLC Method and apparatus for monitoring of an autonomous vehicle
CN109421739A (en) * 2017-08-28 2019-03-05 通用汽车环球科技运作有限责任公司 Method and apparatus for monitoring autonomous vehicle
US20190236865A1 (en) * 2018-01-31 2019-08-01 Mentor Graphics Development (Deutschland) Gmbh Self-diagnosis of faults in an autonomous driving system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113965565A (en) * 2021-09-14 2022-01-21 南京融才交通科技研究院有限公司 Internet of things networking method and system based on information age
WO2024012252A1 (en) * 2022-07-14 2024-01-18 维沃移动通信有限公司 Sensing processing method and apparatus, terminal, network side device, and readable storage medium

Also Published As

Publication number Publication date
US20210124344A1 (en) 2021-04-29
DE102020125596A1 (en) 2021-04-29
US11829128B2 (en) 2023-11-28

Similar Documents

Publication Publication Date Title
US11829128B2 (en) Perception system diagnosis using predicted sensor data and perception results
US9235211B2 (en) Method and arrangement for handover warning in a vehicle having autonomous driving capabilities
US9400897B2 (en) Method for classifying parking scenarios for a system for parking a motor vehicle
US10421399B2 (en) Driver alert systems and methods based on the presence of cyclists
US10339813B2 (en) Display control systems and methods for a vehicle
CN109254283B (en) Detection system and method using ultra-short range radar
US20210035279A1 (en) Perception System Diagnostic Systems And Methods
US10491807B2 (en) Method to use vehicle information and sensors for photography and video viewing recording
US10011211B1 (en) Systems and methods for guiding a boat to a trailer
CN112706746B (en) System and method for detecting and compensating for camera yaw offset of autonomous vehicles
US11618482B2 (en) State determination device, driving support device, state determination method, and driving support method
JP2019168840A (en) Information notification device mountable on vehicle, and vehicle thereof
CN114174123A (en) Vehicle control system
CN108205924B (en) Traffic area consultation system and method
CN108928237B (en) System and method for overriding a vehicle restraint system
US10957189B1 (en) Automatic vehicle alert and reporting systems and methods
US11453417B2 (en) Automated driving control systems and methods based on intersection complexity
US11120646B2 (en) Fault model augmentation systems and methods
US20220236410A1 (en) Lidar laser health diagnostic
US20230142305A1 (en) Road condition detection systems and methods
US11753031B2 (en) Autonomous driving control systems and methods
US11348282B1 (en) Systems and methods for calibrating vehicle cameras using external smart sensor
US20220306139A1 (en) Advanced driving system and feature usage monitoring systems and methods
US11760362B2 (en) Positive and negative reinforcement systems and methods of vehicles for driving
US11325616B2 (en) Driving assistance apparatus and vehicle

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination